As an interdisciplinary subject of medicine and artificial intelligence, intelligent diagnosis and treatment has received extensive attention in both academia and industry. Traditional Chinese medicine (TCM) is characterized by individual syndrome differentiation as well as personalized treatment with personality analysis, which makes the common law mining technology of big data and artificial intelligence appear distortion in TCM diagnosis and treatment study. This article put forward an intelligent diagnosis model of TCM, as well as its construction method. It could not only obtain personal diagnosis varying individually through active learning, but also integrate multiple machine learning models for training, so as to form a more accurate model of learning TCM. Firstly, we used big data extraction technique from different case sources to form a structured TCM database under a unified view. Then, taken a pediatric common disease pneumonia with dyspnea and cough as an example, the experimental analysis on large-scale data verified that the TCM intelligent diagnosis model based on active learning is more accurate than the pre-existing machine learning methods, which may provide a new effective machine learning model for studying TCM diagnosis and treatment.
Objective To investigate the possible role of ulinastatin(UTI) in f lipopolysacccharide (LPS)-induced acute lung injury(ALI).Methods Thirty male SD rats were randomly divided into three groups，ie.a normal control group，a LPS group and a LPS plus UTI group.The rats were injected with 1 mL of normal saline via caudal vein in the control group，with LPS 5 mg/kg via caudal vein in the LPS group，and with UTI 100000 U/kg shortly after injection with LPS in the LPS plus UTI group.The rats were sacrificed 4 h after the injection.Lung wet/dry weight ratio was measured.IL-18 level in serum and lung tissue was determined by ELISA and the expression of NF-κB in lung tissue was determined by immunohistochemistry.Pathological changes of rats’ lung were observed by optical and electron microscope.Results Compared with the control group，IL-18 level in serum and NF-κB expression in lung tissue were significantly higher in the LPS group(Plt;0.01).The IL-8 level was somewhat elevated in the LPS+UTI group but with no significant difference from that in control group was found (Pgt;0.05).The lung inflammation in the LPS+UTI group was milder than that in the LPS rats.Conclusion UTI can alleviate LPS-induced inflammatory reaction and lung injury in rat model.
Purpose To evaluate the correlation of retinal thickness between optical coherence tomography (OCT) images and histologic slides ． Methods Retinal thickness was measured in 16 rabbit retinal histologic slides．The same eyes were previously viewed by OCT for the comparison of results between two methods．Retinal thickness of each OCT image section was measured using both the manually assisted (requiring observer localization of reflectivity peaks) and the automated modes of the computer software． Results Retinal thickness as measured by OCT demonstrated a high degree of correlation with retinal histologic study．The automate d method (gamma;=0．66，P＜0.01) was less reliable than the manually assisted one (gamma;=0．84，P＜0．001)．The former had an error in 95% confidence interval，ranged in-0.71～11.09 mu;m，the latter had a less error，ranged in-2.99～5.13mu;ｍ． Conclusion Retinal thickness can be quantitatively measured by OCT examination．However，computer automatic identification of the reflective boundaries may result in errors in some cases．To measured the retinal thickness by manually assisted mode can increase the degree of accuracy． (Chin J Ocul Fundus Dis，2000，16：71-138)
Glaucoma is one of blind causing diseases. The cup-to-disc ratio is the main basis for glaucoma screening. Therefore, it is of great significance to precisely segment the optic cup and disc. In this article, an optic cup and disc segmentation model based on the linear attention and dual attention is proposed. Firstly, the region of interest is located and cropped according to the characteristics of the optic disc. Secondly, linear attention residual network-34 (ResNet-34) is introduced as a feature extraction network. Finally, channel and spatial dual attention weights are generated by the linear attention output features, which are used to calibrate feature map in the decoder to obtain the optic cup and disc segmentation image. Experimental results show that the intersection over union of the optic disc and cup in Retinal Image Dataset for Optic Nerve Head Segmentation (DRISHTI-GS) dataset are 0.962 3 and 0.856 4, respectively, and the intersection over union of the optic disc and cup in retinal image database for optic nerve evaluation (RIM-ONE-V3) are 0.956 3 and 0.784 4, respectively. The proposed model is better than the comparison algorithm and has certain medical value in the early screening of glaucoma. In addition, this article uses knowledge distillation technology to generate two smaller models, which is beneficial to apply the models to embedded device.
Objective To describe the design and application of an emergency response mobile phone-based information system for infectious disease reporting. Methods Software engineering and business modeling were used to design and develope the emergency response mobile phone-based information system for infectious disease reporting. Results Seven days after the initiation of the reporting system, the reporting rate in the earthquake zone reached the level of the same period in 2007, using the mobile phone-based information system. Surveillance of the weekly report on morbidity in the earthquake zone after the initiation of the mobile phone reporting system showed the same trend as the previous three years. Conclusion The emergency response mobile phone-based information system for infectious disease reporting was an effective solution to transmit urgently needed reports and manage communicable disease surveillance information. This assured the consistency of disease surveillance and facilitated sensitive, accurate, and timely disease surveillance. It is an important backup for the internet-based direct reporting system for communicable disease.
Objective To systematically review the efficacy of long-acting antibacterial material in the prevention of secondary urinary infection. Methods PubMed, The Cochrane Library, CNKI, CBM, WanFang Data and VIP databases were electronically searched to collect randomized controlled trials (RCTs) on the efficacy of long-acting antibacterial material in the prevention of secondary urinary infection from inception to November, 2016. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies, then, meta-analysis was performed by using RevMan 5.3 software. Results A total of 16 RCTs were included. The results of meta-analysis showed that: the long-acting antibacterial material group was superior to the general intervention group in morbidity of secondary urinary infection (Peto OR=0.17, 95%CI 0.13 to 0.23, P<0.000 01), and bacterial positive rate of secondary urinary infection (Peto OR=0.15, 95%CI 0.08 to 0.27,P<0.000 01). Conclusion Current evidence shows that long-acting antibacterial material can effectively reduce the infection rates of secondary urinary infection. Due to limited quality and quantity of the included studies, more high quality studies are needed to verify the above conclusion.